Exploiting Diffusion Prior for Real-World Image Super-Resolution. (arXiv:2305.07015v1 [cs.CV])

We present a novel approach to leverage prior knowledge encapsulated in
pre-trained text-to-image diffusion models for blind super-resolution (SR).
Specifically, by employing our time-aware encoder, we can achieve promising
restoration results without altering the pre-trained synthesis model, thereby
preserving the generative prior and minimizing training cost. To remedy the
loss of fidelity caused by the inherent stochasticity of diffusion models, we
introduce a controllable feature wrapping module that allows users to balance
quality and fidelity by simply adjusting a scalar …

arxiv blind cost diffusion diffusion models encoder generative image image diffusion knowledge loss novel prior synthesis text text-to-image training world